README.md

metadata

license: apache-2.0
library_name: transformers
base_model: rombodawg/Rombos-LLM-V2.6-Qwen-14b
tags:
  - TensorBlock
  - GGUF
model-index:
  - name: Rombos-LLM-V2.6-Qwen-14b
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: HuggingFaceH4/ifeval
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 52.14
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.6-Qwen-14b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: BBH
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 49.22
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.6-Qwen-14b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: hendrycks/competition_math
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 28.85
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.6-Qwen-14b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 17
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.6-Qwen-14b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 19.26
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.6-Qwen-14b
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 48.85
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=rombodawg/Rombos-LLM-V2.6-Qwen-14b
          name: Open LLM Leaderboard

Feedback and support: TensorBlock's Twitter/X, Telegram Group and Discord server

rombodawg/Rombos-LLM-V2.6-Qwen-14b - GGUF

This repo contains GGUF format model files for rombodawg/Rombos-LLM-V2.6-Qwen-14b.

The files were quantized using machines provided by TensorBlock, and they are compatible with llama.cpp as of commit b4011.

Run them on the TensorBlock client using your local machine ↗

Prompt template

<|im_start|>system
{system_prompt}<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Model file specification

Filename	Quant type	File Size	Description
Rombos-LLM-V2.6-Qwen-14b-Q2_K.gguf	Q2_K	5.374 GB	smallest, significant quality loss - not recommended for most purposes
Rombos-LLM-V2.6-Qwen-14b-Q3_K_S.gguf	Q3_K_S	6.202 GB	very small, high quality loss
Rombos-LLM-V2.6-Qwen-14b-Q3_K_M.gguf	Q3_K_M	6.835 GB	very small, high quality loss
Rombos-LLM-V2.6-Qwen-14b-Q3_K_L.gguf	Q3_K_L	7.381 GB	small, substantial quality loss
Rombos-LLM-V2.6-Qwen-14b-Q4_0.gguf	Q4_0	7.933 GB	legacy; small, very high quality loss - prefer using Q3_K_M
Rombos-LLM-V2.6-Qwen-14b-Q4_K_S.gguf	Q4_K_S	7.985 GB	small, greater quality loss
Rombos-LLM-V2.6-Qwen-14b-Q4_K_M.gguf	Q4_K_M	8.371 GB	medium, balanced quality - recommended
Rombos-LLM-V2.6-Qwen-14b-Q5_0.gguf	Q5_0	9.561 GB	legacy; medium, balanced quality - prefer using Q4_K_M
Rombos-LLM-V2.6-Qwen-14b-Q5_K_S.gguf	Q5_K_S	9.561 GB	large, low quality loss - recommended
Rombos-LLM-V2.6-Qwen-14b-Q5_K_M.gguf	Q5_K_M	9.787 GB	large, very low quality loss - recommended
Rombos-LLM-V2.6-Qwen-14b-Q6_K.gguf	Q6_K	11.292 GB	very large, extremely low quality loss
Rombos-LLM-V2.6-Qwen-14b-Q8_0.gguf	Q8_0	14.623 GB	very large, extremely low quality loss - not recommended

Downloading instruction

Command line

Firstly, install Huggingface Client

pip install -U "huggingface_hub[cli]"

Then, downoad the individual model file the a local directory

huggingface-cli download tensorblock/Rombos-LLM-V2.6-Qwen-14b-GGUF --include "Rombos-LLM-V2.6-Qwen-14b-Q2_K.gguf" --local-dir MY_LOCAL_DIR

If you wanna download multiple model files with a pattern (e.g., *Q4_K*gguf), you can try:

huggingface-cli download tensorblock/Rombos-LLM-V2.6-Qwen-14b-GGUF --local-dir MY_LOCAL_DIR --local-dir-use-symlinks False --include='*Q4_K*gguf'